Abstract
We discuss a simple strategy aimed at improving neural network prediction accuracy, based on the combination of predictions at varying resolution levels of the domain under investigation (here: time series). First, a wavelet transform is used to decompose the time series into varying scales of temporal resolution. The latter provides a sensible decomposition of the data so that the underlying temporal structures of the original time series become more tractable. Then, a dynamical recurrent neural netork is trained on each resolution scale with the temporal-recurrent backpropagation algorithm. By virtue of its internal dynamic, this general class of dynamic connections network approximates the underlying law governing each resolution level by a system of non-linear difference equations. The individual wavelet scale forecasts are afterwards recombined to form the current estimate. The predictive ability of this strategy is assessed with the sunspot series.
Original language | English |
---|---|
Pages (from-to) | 113-122 |
Number of pages | 10 |
Journal | Connection Science |
Volume | 9 |
Issue number | 1 |
DOIs | |
Publication status | Published - Mar 1997 |
Externally published | Yes |